检索结果-内蒙古大学图书馆

Electrical, Energy, and Artificial Intelligence (EICEEAI), International Engineering Conference on

作者： Dalia Alzu'bi Rabia Emhamed Al Mamlook Ahmad Nasayreh Mohammad Aljaidi Rami AlAzab Hasan Gharaibeh Qais Al-Na'amneh Dep. Information and Systems Engineering Concordia University Montreal Canada Dep. of Business Administration Trine University Indiana USA Department of Industrial Engineering University Zawia Tripoli Libia Dep. Computer Science Yarmouk University Irbid Jordan Dep. of Computer Science Zarqa University Zarqa Jordan Dep. Surgery and Urology Jordan University of Science and Technology Irbid Jordan Dep. of Cyber Security Applied Science Private University Amman Jordan

ISBN: (数字)9798350373363

ISBN: (纸本)9798350373370

The kidneys have the important function of filtering waste products and toxins from the blood in the human body. Any problems affecting the kidneys can potentially impact their efficiency and overall function. Kidney Tumor (KT) is a disease that specifically affects kidney cells and causes the abnormal growth of tissue in one or both kidneys. Assessing the risk of developing a kidney tumor and identifying the key factors that contribute to this risk are crucial for ensuring patient well-being. Additionally, this information assists doctors and specialists in making faster and more accurate diagnoses, determining appropriate treatment methods, and potentially influencing the course of the disease to minimize its severity and impact. Machine learning algorithms have recently been introduced to evaluate disease risks, and in this study, we specifically focus on examining the risk of kidney tumor development and investigating the influencing factors. We employed a logistic regression model to predict if a patient is at risk of developing a kidney tumor or not, and further categorized the samples into high-risk and low-risk groups. Our model was trained and tested using a unique dataset obtained from the (KAUH) hospital in Jordan, consisting of well-balanced metadata from 120 patients with kidney issues. Our work demonstrated accuracy results ranging from 90% to 98%. Ultimately, specialists can utilize our model as an additional tool to enhance the speed and accuracy of patient diagnoses

关键词： Logistic regression Analytical models Accuracy Predictive models Genetics History Reliability

来源：评论

学校读者我要写书评

暂无评论

BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning

arXiv

引用

arXiv 2023年

作者： Jeeveswaran, Kishaan Bhat, Prashant Zonooz, Bahram Arani, Elahe Advanced Research Lab NavInfo Europe Netherlands Dep. of Mathematics and Computer Science Eindhoven University of Technology Netherlands

The ability of deep neural networks to continually learn and adapt to a sequence of tasks has remained challenging due to catastrophic forgetting of previously learned tasks. Humans, on the other hand, have a remarkable ability to acquire, assimilate, and transfer knowledge across tasks throughout their lifetime without catastrophic forgetting. The versatility of the brain can be attributed to the rehearsal of abstract experiences through a complementary learning system. However, representation rehearsal in vision transformers lacks diversity, resulting in overfitting and consequently, performance drops significantly compared to raw image rehearsal. Therefore, we propose BiRT, a novel representation rehearsal-based continual learning approach using vision transformers. Specifically, we introduce constructive noises at various stages of the vision transformer and enforce consistency in predictions with respect to an exponential moving average of the working model. Our method provides consistent performance gain over raw image and vanilla representation rehearsal on several challenging CL benchmarks, while being memory efficient and robust to natural and adversarial corruptions. 1 © 2023, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal

arXiv

引用

arXiv 2023年

作者： Gurulingan, Naresh Kumar Zonooz, Bahram Arani, Elahe Advanced Research Lab NavInfo Europe Netherlands Dep. of Mathematics and Computer Science Eindhoven University of Technology Netherlands

Multi-task learning has the potential to improve generalization by maximizing positive transfer between tasks while reducing task interference. Fully achieving this potential is hindered by manually designed architectures that remain static throughout training. On the contrary, learning in the brain occurs through structural changes that are in tandem with changes in synaptic strength. Thus, we propose Multi-Task Structural Learning (MTSL) that simultaneously learns the multi-task architecture and its parameters. MTSL begins with an identical single-task network for each task and alternates between a task-learning phase and a structural-learning phase. In the task learning phase, each network specializes in the corresponding task. In each of the structural learning phases, starting from the earliest layer, locally similar task layers first transfer their knowledge to a newly created group layer before being removed. MTSL then uses the group layer in place of the corresponding removed task layers and moves on to the next layers. Our empirical results show that MTSL achieves competitive generalization with various baselines and improves robustness to out-of-distribution data. Code available at https://***/NeurAI-Lab/MTSL. © 2023, CC BY-NC-ND.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

TASK-AWARE INFORMATION ROUTING FROM COMMON REPRESENTATION SPACE IN LIFELONG LEARNING

arXiv

引用

arXiv 2023年

作者： Bhat, Prashant Zonooz, Bahram Arani, Elahe Advanced Research Lab NavInfo Europe Netherlands Dep. of Mathematics and Computer Science Eindhoven University of Technology Netherlands

Intelligent systems dep.oyed in the real world suffer from catastrophic forgetting when exposed to a sequence of tasks. Humans, on the other hand, acquire, consolidate, and transfer knowledge between tasks that rarely interfere with the consolidated knowledge. Accompanied by self-regulated neurogenesis, continual learning in the brain is governed by a rich set of neurophysiological processes that harbor different types of knowledge, which are then integrated by conscious processing. Thus, inspired by the Global Workspace Theory of conscious information access in the brain, we propose TAMiL, a continual learning method that entails task-attention modules to capture task-specific information from the common representation space. We employ simple, undercomplete autoencoders to create a communication bottleneck between the common representation space and the global workspace, allowing only the task-relevant information to the global workspace, thus greatly reducing task interference. Experimental results show that our method outperforms state-of-the-art rehearsal-based and dynamic sparse approaches and bridges the gap between fixed capacity and parameter isolation approaches while being scalable. We also show that our method effectively mitigates catastrophic forgetting while being well-calibrated with reduced task-recency bias. © 2023, CC BY-NC-ND.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

ERROR SENSITIVITY MODULATION BASED EXPERIENCE REPLAY: MITIGATING ABRUPT REPRESENTATION DRIFT IN CONTINUAL LEARNING

arXiv

引用

arXiv 2023年

作者： Sarfraz, Fahad Arani, Elahe Zonooz, Bahram Advanced Research Lab NavInfo Europe Netherlands Dep. of Mathematics and Computer Science Eindhoven University of Technology Netherlands

Humans excel at lifelong learning, as the brain has evolved to be robust to distribution shifts and noise in our ever-changing environment. Deep neural networks (DNNs), however, exhibit catastrophic forgetting and the learned representations drift drastically as they encounter a new task. This alludes to a different error-based learning mechanism in the brain. Unlike DNNs, where learning scales linearly with the magnitude of the error, the sensitivity to errors in the brain decreases as a function of their magnitude. To this end, we propose ESMER which employs a principled mechanism to modulate error sensitivity in a dual-memory rehearsal-based system. Concretely, it maintains a memory of past errors and uses it to modify the learning dynamics so that the model learns more from small consistent errors compared to large sudden errors. We also propose Error-Sensitive Reservoir Sampling to maintain episodic memory, which leverages the error history to pre-select low-loss samples as candidates for the buffer, which are better suited for retaining information. Empirical results show that ESMER effectively reduces forgetting and abrupt drift in representations at the task boundary by gradually adapting to the new task while consolidating knowledge. Remarkably, it also enables the model to learn under high levels of label noise, which is ubiquitous in real-world data streams. Code: https://***/NeurAI-Lab/ESMER. © 2023, CC BY-NC-ND.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Poster: Selection of Optimal Neural Model using Spiking Neural Network for Edge Computing*

Poster: Selection of Optimal Neural Model using Spiking Neur...

引用

International Conference on Distributed Computing Systems

作者： Sanaullah Kaushik Roy Ulrich Ruckert Thorsten Jungeblut Dep. of Eng. and Math. Industrial IOT University of Applied Sciences and Arts Bielefeld Germany Dep. of Computer Science Cyber Defense and AI Lab Lab North Carolina A&T State University NC USA Dep. of Faculty of Technology Cognitive Interaction Technology Universitat Bielefeld Bielefeld Germany

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

Spiking Neural Networks (SNNs), are inspired by the biological brain's complicated signaling mechanisms and possess unique characteristics that set them apart from traditional artificial neural networks. This research study explores the challenging domain of image classification, specifically utilizing the well-known MNIST dataset through the development and thorough evaluation of different neural models for edge computing. However, the primary contribution is the autonomous selection of the best-performing SNN model through various early stopping approaches and validation functions, allowing the models to autonomously adapt during training. In addition, this article presents the standalone AutoML-SNN model, which is the introduction of dynamic elements into selected SNN domains, enhancing their adaptability to complex patterns within the dataset. Furthermore, the early stopping methodologies are used to reduce overfitting hazards, and using the 3000-neuron set, the LIF appeared as the most proficient neural model.

关键词： Training Adaptation models Computational modeling Biological system modeling Neurons Spiking neural networks Hazards

来源：评论

学校读者我要写书评

暂无评论

GUI-PV Application Tool for Teaching Performance of PV System using MATLAB-Graphical User Interface Environment 1

GUI-PV Application Tool for Teaching Performance of PV Syste...

引用

1st IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and computer Engineering, MI-STA 2021

作者： Almaktoof, Ali Shebani, Nafaa Elfallah, Ali Cape Peninsula University of Technology Electrical Electronics and Computer Engineering Dep. Cape Town South Africa

ISBN: (纸本)9781665418560

A MATLAB-Graphical User Interface (GUI) based educational software which could aid in the analysis and education of photovoltaic (PV) modules is presented in this paper. The MATLAB-GUI for studying the PV module based on the evaluation of the current, voltage and power characteristics as well as performance evaluation of the PV module under different values of radiation and temperature are presented. The Graphical User Interface-Photovoltaic (GUI-PV) application is developed to simulate the characteristics of PV module and show the effects of temperature and solar radiation on the PV modules. In addition, the GUI-PV can provide PV module specifications and parameters including maximum power, current and voltage, fill factor and efficiency,...etc. Two GUI-PV models are developed for PV module characteristics and performance evaluation of solar module. Testing of the GUI-PV platform exposes that students who are trained using GUI-PV software easily understood the concept of a solar PV panel and defined the maximum power of the solar photovoltaic modules and some other parameters. © 2021 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Knowledge Representation of Asset Information and Performance in OT Environments

Knowledge Representation of Asset Information and Performanc...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Mukund Bhole Wolfgang Kastner Thilo Sauter Institute of Computer Engineering TU Wien Vienna Austria Institute of Computer Technology TU Wien Dep. of Integrated Sensor Systems Danube University Krems Austria

To make a management decision for the Operational technology (OT) environment, obtaining OT asset information from a plant is essential. Key Performance Indicators (KPIs) can play a crucial role in evaluating the performance of the manufacturing process, minimizing production costs, assessing process effectiveness, and investigating various settings to improve performance, operations, and quality in OT. This paper aims to provide a detailed examination of how Asset Information Mining Sources (AIMSs) support the process for acquiring both static and runtime OT asset information. Once we have obtained accurate OT asset information, we can calculate the KPIs and incorporate them into a knowledge representation using an ontology-based model. This model can assist the management team in making informed decisions and provide a roadmap for exploring further automation possibilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Model Based Framework for Testing Safety and Security in Operational technology Environments

arXiv

引用

arXiv 2023年

作者： Bhole, Mukund Kastner, Wolfgang Sauter, Thilo Institute of Computer Engineering TU Wien Vienna Austria Institute of Computer Technology TU Wien Dep. of Integrated Sensor Systems Danube University Krems Austria

Today’s industrial control systems consist of tightly coupled components allowing adversaries to exploit security attack surfaces from the information technology side, and, thus, also get access to automation devices residing at the operational technology level to compromise their safety functions. To identify these concerns, we propose a model-based testing approach which we consider a promising way to analyze the safety and security behavior of a system under test providing means to protect its components and to increase the quality and efficiency of the overall system. The structure of the underlying framework is divided into four parts, according to the critical factors in testing of operational technology environments. As a first step, this paper describes the ingredients of the envisioned framework. A system model allows to overview possible attack surfaces, while the foundations of testing and the recommendation of mitigation strategies will be based on process-specific safety and security standard procedures with the combination of existing vulnerability databases. © 2023, CC BY.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Automated Crop Harvesting, Growth Monitoring and Disease Detection System for Vertical Farming Greenhouse 3

Automated Crop Harvesting, Growth Monitoring and Disease Det...

引用

3rd International Conference on Advancements in Computing, ICAC 2021

作者： Jayasekara, Charith Banneka, Sajani Pasindu, Gihan Udawaththa, Yukthi Wellalage, Sasini Abeygunawardhane, Pradeep K.W. Sri Lanka Institute of Information Technology Dep. of Computer Systems Engineering Malabe10115 Sri Lanka

ISBN: (纸本)9781665408622

Greenhouses are a type of cultivation method used to optimize the production of crops by using controlled climatic conditions and other external factors. They are widely used in agriculture both globally and locally. Vertical farming is the modern practice of growing crops in vertically stacked layers in warehouses that aims to optimize and develop plant growth by using controlled environment agriculture. This type of agriculture concept is practiced in Sri Lanka at present. This research paper proposes a robot which consists of a specific navigation system and harvesting mechanism that can be used inside greenhouses. The proposed system can be implemented to harvest lettuce in the vertical farming greenhouses where lettuce needs to be harvested with care to ensure the supermarket quality. The above-mentioned system helps to detect the diseases of plants also where a lot of time can be saved, and less effort is made with the use of this type of implementation. © 2021 IEEE.

关键词： Greenhouses

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：